© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47321
    Prev
    Next
    INDEX
    Explanations

    at your option

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively responds to numeric identifiers (e.g. citation codes, section or figure numbers, version numbers) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mx
    -0.75
     Wohnung
    -0.74
     MX
    -0.69
     Mx
    -0.65
    Unspecified
    -0.62
     dirinya
    -0.62
    朧
    -0.61
     詩
    -0.60
    HEX
    -0.59
    LIMITED
    -0.59
    POSITIVE LOGITS
    glBindTexture
    0.69
    bürger
    0.68
     Maus
    0.66
    ้ง
    0.66
    kijken
    0.65
    écart
    0.65
    联
    0.65
    リ
    0.65
     міс
    0.64
     سفید
    0.64
    Activations Density 0.053%

    No Known Activations